YenJJ commited on
Commit
896d4ec
1 Parent(s): ddf1cdd

Training in progress, epoch 0

Browse files
Files changed (3) hide show
  1. config.json +26 -16
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,33 +1,43 @@
1
  {
2
- "_name_or_path": "distilbert/distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
  "id2label": {
12
  "0": "NEGATIVE",
13
  "1": "POSITIVE"
14
  },
15
  "initializer_range": 0.02,
 
16
  "label2id": {
17
  "NEGATIVE": 0,
18
  "POSITIVE": 1
19
  },
 
20
  "max_position_embeddings": 512,
21
- "model_type": "distilbert",
22
- "n_heads": 12,
23
- "n_layers": 6,
 
 
24
  "pad_token_id": 0,
25
- "problem_type": "single_label_classification",
26
- "qa_dropout": 0.1,
27
- "seq_classif_dropout": 0.2,
28
- "sinusoidal_pos_embds": false,
29
- "tie_weights_": true,
 
 
 
 
 
 
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.44.2",
32
- "vocab_size": 30522
 
33
  }
 
1
  {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
 
3
  "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
  "id2label": {
11
  "0": "NEGATIVE",
12
  "1": "POSITIVE"
13
  },
14
  "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
  "label2id": {
17
  "NEGATIVE": 0,
18
  "POSITIVE": 1
19
  },
20
+ "layer_norm_eps": 1e-07,
21
  "max_position_embeddings": 512,
22
+ "max_relative_positions": -1,
23
+ "model_type": "deberta-v2",
24
+ "norm_rel_ebd": "layer_norm",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
  "pad_token_id": 0,
28
+ "pooler_dropout": 0,
29
+ "pooler_hidden_act": "gelu",
30
+ "pooler_hidden_size": 768,
31
+ "pos_att_type": [
32
+ "p2c",
33
+ "c2p"
34
+ ],
35
+ "position_biased_input": false,
36
+ "position_buckets": 256,
37
+ "relative_attention": true,
38
+ "share_att_key": true,
39
  "torch_dtype": "float32",
40
  "transformers_version": "4.44.2",
41
+ "type_vocab_size": 0,
42
+ "vocab_size": 128100
43
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f97bb94a5658e5cc2236a62f48304ea20e0cc88cc7b623d66d5cecf543e7ab23
3
- size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dacca455e3007efc84b3b6314339018455acab291384fcf143a58296458a14c
3
+ size 737719272
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb6826d11720a89cbde8266081eadf74854625a38440541d92790ec3c357db3f
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a733d3749c76364f4ba470d9908541dd835aac00acef0b3ecadd33c81a9d563
3
  size 5176